Displaying 3 results from an estimated 3 matches for "fsvrps".
2013 Jan 02
0
[LLVMdev] [DragonEgg] [Polly] Should we expect DragonEgg to produce identical LLVM IR for identical GIMPLE?
...- Number of regions that a valid part of Scop
<------------------ __kernelgen_main_loop_17: compile completed
------------------->
It works pretty well in many situations, but in this particular case it
does not help. Those problematic "Fortran scalar values referred by
pointers" (FSVRPs) can only substituted (replaced by actual value) after
proper memory analysis. According to current design, memory analysis
operates on SCoPs, but Polly is already unable to detect SCoP for the whole
group of nested loops due to presence of those FSVRPs. So, chicken and egg
problem.
- D.
2013/1/2...
2013 Jan 02
2
[LLVMdev] [DragonEgg] [Polly] Should we expect DragonEgg to produce identical LLVM IR for identical GIMPLE?
On 01/01/2013 02:45 PM, Duncan Sands wrote:
> Hi Dmitry,
>
>>
>> In our compiler we use a modified version LLVM Polly, which is very
>> sensitive to
>> proper code generation. Among the number of limitations, the loop region
>> (enclosed by phi node on induction variable and branch) is required to
>> be free
>> of additional memory-dependent
2013 Jan 04
4
[LLVMdev] [Polly] Aliasing problems escalation (WAS: Re: [DragonEgg] [Polly] Should we expect DragonEgg to produce identical LLVM IR for identical GIMPLE?)
...alid part of Scop
> <------------------ __kernelgen_main_loop_17: compile completed
> ------------------->
>
> It works pretty well in many situations, but in this particular case it
> does not help. Those problematic "Fortran scalar values referred by
> pointers" (FSVRPs) can only substituted (replaced by actual value) after
> proper memory analysis. According to current design, memory analysis
> operates on SCoPs, but Polly is already unable to detect SCoP for the whole
> group of nested loops due to presence of those FSVRPs. So, chicken and egg
> prob...